Christophe Thiéry [Tue, 15 Nov 2011 22:00:44 +0000 (23:00 +0100)]
Lua: fix Chord example
Christophe Thiéry [Tue, 15 Nov 2011 17:57:13 +0000 (18:57 +0100)]
Nobody uses MSG_get_errno and wants useless calls to SIMIX_process_self
Christophe Thiéry [Tue, 15 Nov 2011 17:22:05 +0000 (18:22 +0100)]
SIMIX: add a redundant parameter to avoid repeated SIMIX_process_self()
Christophe Thiéry [Tue, 15 Nov 2011 15:54:33 +0000 (16:54 +0100)]
Remove a useless function. The default one does the same thing.
Martin Quinson [Tue, 15 Nov 2011 16:15:03 +0000 (17:15 +0100)]
plug some more memleaks. We have no leak on the GOAL example anymore, yuhu
Navarrop [Tue, 15 Nov 2011 15:18:37 +0000 (16:18 +0100)]
Add a platform with a bypass route. Add the test to cmake.
Update flatifier and basic_parsing_test to not put "\t" but spaces.
Martin QUINSON [Tue, 15 Nov 2011 14:54:08 +0000 (15:54 +0100)]
forgot to recreate the option when reviving supernovae
Martin Quinson [Tue, 15 Nov 2011 14:43:55 +0000 (15:43 +0100)]
revert [
a30523e] (remove supernovae) because I need some timings on G5K, and fix what broke in supernovae mode since then
Martin Quinson [Tue, 15 Nov 2011 13:34:45 +0000 (14:34 +0100)]
plug some more memleaks. aint bad anymore
Christophe Thiéry [Tue, 15 Nov 2011 13:28:29 +0000 (14:28 +0100)]
Lua: removing the MSG_process_sleep hack changes the order of output
Christophe Thiéry [Tue, 15 Nov 2011 13:23:43 +0000 (14:23 +0100)]
Lua: copy tasks so that the sender doesn't have to sleep
This will allow to implement asynchronous comms (isend/irecv)
Christophe Thiéry [Tue, 15 Nov 2011 13:18:28 +0000 (14:18 +0100)]
Cosmetics
Martin Quinson [Tue, 15 Nov 2011 12:14:28 +0000 (13:14 +0100)]
plug a bunch of memleaks
Martin Quinson [Tue, 15 Nov 2011 11:04:08 +0000 (12:04 +0100)]
damn it, there is no example testing the bypass mecanism!!
Martin Quinson [Tue, 15 Nov 2011 10:48:41 +0000 (11:48 +0100)]
replace a new/free cycle by a locally stacked object
Martin Quinson [Tue, 15 Nov 2011 10:41:26 +0000 (11:41 +0100)]
work to enforce that link arg is readily usable in r_g_r_a_l
Martin Quinson [Tue, 15 Nov 2011 10:28:19 +0000 (11:28 +0100)]
reduce the dynar creation madness in g_r_a_l in recursive case
Martin Quinson [Tue, 15 Nov 2011 09:43:04 +0000 (10:43 +0100)]
rewrite an error message
Martin Quinson [Tue, 15 Nov 2011 09:36:22 +0000 (10:36 +0100)]
merge get_route and get_latency in routings too
Martin Quinson [Tue, 15 Nov 2011 08:52:40 +0000 (09:52 +0100)]
rename a global to avoid namespace pollution (and other cosmetics)
Martin Quinson [Tue, 15 Nov 2011 08:43:42 +0000 (09:43 +0100)]
kill useless asserts: this is not the way routing logics will take to notice about non-existant routes
Martin Quinson [Tue, 15 Nov 2011 08:40:58 +0000 (09:40 +0100)]
further streamline r_get_route_a_l: now that latency is nicely additive, no need for extra precaution
Martin Quinson [Tue, 15 Nov 2011 08:36:10 +0000 (09:36 +0100)]
simplify _routing_get_route_and_latency wrt latency
- remove duplicated asserts about non negative latency
routing_get_route_and_latency (w/o _) checks it
- give the responsability to initialize it to the caller
- streamline the code
Martin Quinson [Tue, 15 Nov 2011 08:15:09 +0000 (09:15 +0100)]
Change again the calling convention of routing_get_route_and_latency
now, you cannot call it without passing a valid route receiver. It
will be created if pointing to NULL, or simply filled. Actually that
was the de facto calling convention in the code.
This allows to simplify routing_get_route_and_latency by not checking
if the caller is interested in the route at every line.
(plus some useless cosmetics)
Martin Quinson [Tue, 15 Nov 2011 07:45:05 +0000 (08:45 +0100)]
check that AS->get_route don't return NULL on non-existant route, but throw an exception
Martin Quinson [Tue, 15 Nov 2011 01:35:50 +0000 (02:35 +0100)]
kill the now useless 'cleanup' parameter of routing_get_route_and_latency
Instead, if route == NULL we won't bother collecting the route, so
freeing is useless.
If *route == NULL, we create a short-lived dynar (equivalent to the
result of having cleanup=1 previously
else, we fill that route without messing with it
Martin Quinson [Tue, 15 Nov 2011 01:06:53 +0000 (02:06 +0100)]
kill global_routing->get_route_no_cleanup()
use routing_get_route_and_latency(....., 0) instead
Martin Quinson [Tue, 15 Nov 2011 01:01:25 +0000 (02:01 +0100)]
kill routing_get_route(), use routing_get_route_and_latency() instead
Martin Quinson [Tue, 15 Nov 2011 00:35:56 +0000 (01:35 +0100)]
AS->get_route is no longer in charge of creating the route it fills
The whole idea is to reduce the dynar creation, copy, destroy madness
in the router. This step is only the first one on that way.
It may well happen that this change leads to massive memleaks. I'll
check after this later.
Martin Quinson [Mon, 14 Nov 2011 23:31:49 +0000 (00:31 +0100)]
simplification + add comments + reindent of _get_route_and_latency
Martin Quinson [Mon, 14 Nov 2011 23:16:07 +0000 (00:16 +0100)]
useless cosmetics
Martin Quinson [Mon, 14 Nov 2011 16:40:03 +0000 (17:40 +0100)]
pre-parse the vivaldi coordinates
Martin Quinson [Mon, 14 Nov 2011 16:05:55 +0000 (17:05 +0100)]
another empty function murder
Martin Quinson [Mon, 14 Nov 2011 16:01:02 +0000 (17:01 +0100)]
nah, properties in the XML file are not the right place to pass configuration options
Actually, the properties are the right location, but only when
included in a config tag. And in this setting, the right behavior is
already done by the </config> handler, no need to also do it for the
generic <prop> handler. Doing so anyway would prevent to pass
"coordinates" (user-)properties to hosts, links and such.
Martin Quinson [Mon, 14 Nov 2011 15:58:02 +0000 (16:58 +0100)]
don't trust globals to be memset'ed to 0 (and rework a message)
Martin Quinson [Mon, 14 Nov 2011 15:50:13 +0000 (16:50 +0100)]
error message rewrite
Martin Quinson [Mon, 14 Nov 2011 15:48:12 +0000 (16:48 +0100)]
Let's trust the mathematics here: sqrt + fabs + fabs IS positive or nul :)
Martin Quinson [Mon, 14 Nov 2011 15:42:43 +0000 (16:42 +0100)]
tiny cleanups, and add a FIXME
Martin Quinson [Mon, 14 Nov 2011 15:31:41 +0000 (16:31 +0100)]
merge structures route_t and route_extended_t.
All this added complexity to save 2 pointers was a bit too much for
me. Yeah, YMMV, but I prefer it this way.
Martin Quinson [Mon, 14 Nov 2011 14:56:53 +0000 (15:56 +0100)]
tiny function renaming
Martin Quinson [Mon, 14 Nov 2011 19:20:17 +0000 (20:20 +0100)]
fix the breakages that were hidden because some tests were disabled
Martin Quinson [Mon, 14 Nov 2011 16:15:53 +0000 (17:15 +0100)]
pcre is not optional anymore since a while -- reactivate the vivaldi tests
Christophe Thiéry [Mon, 14 Nov 2011 15:48:39 +0000 (16:48 +0100)]
Lua: implementing asynchronous comms (wait, test, isend, dsend, irecv)
Christophe Thiéry [Mon, 14 Nov 2011 14:28:07 +0000 (15:28 +0100)]
Lua: add a function simgrid.process.sleep()
Christophe Thiéry [Mon, 14 Nov 2011 14:10:41 +0000 (15:10 +0100)]
Lua: add a function simgrid.get_clock()
Christophe Thiéry [Mon, 14 Nov 2011 13:51:33 +0000 (14:51 +0100)]
Lua: document the possibility to use numbers for mailboxes
Christophe Thiéry [Mon, 14 Nov 2011 13:38:26 +0000 (14:38 +0100)]
Lua: return errors from execute/send/recv, or nil in case of success
Christophe Thiéry [Mon, 14 Nov 2011 13:03:26 +0000 (14:03 +0100)]
Lua: rename simgrid.task.name() to simgrid.task.get_name()
Christophe Thiéry [Mon, 14 Nov 2011 12:57:18 +0000 (13:57 +0100)]
Lua Chord example (not working yet, the API is still incomplete)
Christophe Thiéry [Mon, 14 Nov 2011 10:22:08 +0000 (11:22 +0100)]
Make MSG_TASK_CANCELLED deprecated, replace it by MSG_TASK_CANCELED
Navarrop [Mon, 14 Nov 2011 16:13:52 +0000 (17:13 +0100)]
Remove ruby example from simgrid.
Arnaud Giersch [Mon, 14 Nov 2011 14:37:41 +0000 (15:37 +0100)]
Use xbt_XXX_is_empty() instead of testing xbt_XXX_length() against 0.
Where XXX is 'dict' or 'dynar'.
(was a request from emptty)
Arnaud Giersch [Mon, 14 Nov 2011 11:01:11 +0000 (12:01 +0100)]
Rewrite xbt libs, using xbt dicts.
And remove lots of code duplication.
Also remove unused functions.
Arnaud Giersch [Mon, 14 Nov 2011 10:23:25 +0000 (11:23 +0100)]
Use xbt_lib_length instead of xbt_lib_size.
Arnaud Giersch [Mon, 14 Nov 2011 10:21:06 +0000 (11:21 +0100)]
Use defined interface for accessing to lib properties.
Arnaud Giersch [Mon, 14 Nov 2011 12:04:16 +0000 (13:04 +0100)]
Remove usage of xbt_dict_size().
xbt_dict_size() can now be safely removed.
Arnaud Giersch [Mon, 14 Nov 2011 12:10:51 +0000 (13:10 +0100)]
Remove trailing spaces in ChangeLog.
Laurent Bobelin [Sat, 12 Nov 2011 09:02:21 +0000 (10:02 +0100)]
Added the new logo to the unstable doc, so that Lucas and Fred can show a webpage and at least one doc with the same logo at SC
Martin Quinson [Fri, 11 Nov 2011 08:37:49 +0000 (09:37 +0100)]
kill another "method" away from the "singleton" global_routing
OO coding in C is something, but applying the worst possible OO design
to C is ... inventive
Martin Quinson [Fri, 11 Nov 2011 02:36:28 +0000 (03:36 +0100)]
cosmetics and improve doc
Martin Quinson [Fri, 11 Nov 2011 02:31:05 +0000 (03:31 +0100)]
kill a file that were begging for it
Martin Quinson [Fri, 11 Nov 2011 02:18:51 +0000 (03:18 +0100)]
cosmetics
Martin Quinson [Fri, 11 Nov 2011 02:17:41 +0000 (03:17 +0100)]
move the callbacks to the cluster creation from surfxml_parse to sg_platf
Martin Quinson [Fri, 11 Nov 2011 02:05:27 +0000 (03:05 +0100)]
I've found the name of the next release
Martin Quinson [Fri, 11 Nov 2011 01:47:04 +0000 (02:47 +0100)]
move some XML specific code from surf_routing.c to surfxml_parse.c
Martin Quinson [Fri, 11 Nov 2011 01:37:58 +0000 (02:37 +0100)]
Improve a bit the documentation of hte xbt_queues, and ensure that they are displayed on the web site
Arnaud Giersch [Thu, 10 Nov 2011 22:53:50 +0000 (23:53 +0100)]
Remove two more declaration of phantom functions.
Arnaud Giersch [Thu, 10 Nov 2011 22:36:16 +0000 (23:36 +0100)]
Simply say fun_ptr(...) instead of (*fun_ptr)(...).
Another possible cleanup in the same spirit is to remove the
ampersand when taking the address of a function.
This is left as an exercise for the reader.
Martin Quinson [Thu, 10 Nov 2011 22:07:03 +0000 (23:07 +0100)]
some more cleanups for tomorrow marked as FIXME for now -- good night
Martin Quinson [Thu, 10 Nov 2011 22:03:25 +0000 (23:03 +0100)]
various psychorigid cleanups -- routing_parse_cluster() is now readable
Martin Quinson [Thu, 10 Nov 2011 21:52:03 +0000 (22:52 +0100)]
that's a quite complicated no-op :)
Martin Quinson [Thu, 10 Nov 2011 21:40:23 +0000 (22:40 +0100)]
Merge branch 'parser'
Martin Quinson [Thu, 10 Nov 2011 21:38:52 +0000 (22:38 +0100)]
do not search the cluster backbones again and again, store them in the right location
On the poor tests I've done, it seems to give a non negligible
improvement on the goal example. Maybe 5-10%, but it's hard to say
right now.
Martin Quinson [Thu, 10 Nov 2011 21:23:25 +0000 (22:23 +0100)]
you have to plug the memleaks from time to time
Martin Quinson [Thu, 10 Nov 2011 21:03:36 +0000 (22:03 +0100)]
populate the routing_none_finalize to make sure that we always call these functions
Martin Quinson [Thu, 10 Nov 2011 20:54:20 +0000 (21:54 +0100)]
cosmetics: variable&fields renaming
Martin Quinson [Thu, 10 Nov 2011 20:39:19 +0000 (21:39 +0100)]
Use the none routing as an ancestor to the generic one, which is ancestor to most of the others. First step to further factorization
Martin Quinson [Thu, 10 Nov 2011 20:30:43 +0000 (21:30 +0100)]
cosmetics, nothing serious
Christophe Thiéry [Thu, 10 Nov 2011 17:46:50 +0000 (18:46 +0100)]
New Lua example: Chord (work in progress)
Martin Quinson [Thu, 10 Nov 2011 17:42:59 +0000 (18:42 +0100)]
sanitize get_network_element_type()
It were declared as a field of global_routing, and of each and every
routing model. That's a bit much for a simple little function.
Martin Quinson [Thu, 10 Nov 2011 17:07:38 +0000 (18:07 +0100)]
kill unused global_routing->get_latency()
Martin Quinson [Thu, 10 Nov 2011 17:05:39 +0000 (18:05 +0100)]
Kill global_routing->get_route_or_null
It was used at only one location, so I setup a TRY/CATCH in there
instead
Martin Quinson [Thu, 10 Nov 2011 16:57:02 +0000 (17:57 +0100)]
That pointer to function was never given anything but one value
The global_routing value seem to be used to group functions together,
but the fields cannot be given another value.
Of course, I'm gonna kill em all.
Martin Quinson [Thu, 10 Nov 2011 16:47:24 +0000 (17:47 +0100)]
factorize the routing_exit functionality, and ensure that no model can forget to call it
Martin Quinson [Thu, 10 Nov 2011 16:37:30 +0000 (17:37 +0100)]
kill small crufts here and there
Martin Quinson [Thu, 10 Nov 2011 16:33:46 +0000 (17:33 +0100)]
kill further globals
Martin Quinson [Thu, 10 Nov 2011 16:20:36 +0000 (17:20 +0100)]
saner pattern use in the trace files
I guess that previously, the patterns were replaced for the first
host, and then reused as is for the next ones. So the traces specified
for the first host were used for any ones.
Martin Quinson [Thu, 10 Nov 2011 16:20:04 +0000 (17:20 +0100)]
fix the constness of xbt_strbuff_new_from(), it's too dangerous with previous prototype
Martin Quinson [Thu, 10 Nov 2011 16:07:48 +0000 (17:07 +0100)]
various cleanups
amongst other, kill yet another global
Martin Quinson [Thu, 10 Nov 2011 15:56:00 +0000 (16:56 +0100)]
ahah. Mort de rire. :-/
Martin Quinson [Thu, 10 Nov 2011 15:54:43 +0000 (16:54 +0100)]
various cleanups and clarifications
Martin Quinson [Thu, 10 Nov 2011 15:51:03 +0000 (16:51 +0100)]
rename routing_component to as, since that's just an AS at the end of the day
Navarrop [Thu, 10 Nov 2011 16:39:07 +0000 (17:39 +0100)]
Remove section about java.
Navarrop [Thu, 10 Nov 2011 16:14:03 +0000 (17:14 +0100)]
Make a sync in a different directory.
Christophe Thiéry [Thu, 10 Nov 2011 15:47:20 +0000 (16:47 +0100)]
Lua masterslave: simplify the code and improve the output
Christophe Thiéry [Thu, 10 Nov 2011 15:45:04 +0000 (16:45 +0100)]
Lua: set a task metatable that allows OO-style syntax
You can now write my_task:send(mailbox), which is just syntaxic sugar
for simgrid.task.send(my_task, mailbox).
Christophe Thiéry [Thu, 10 Nov 2011 14:54:02 +0000 (15:54 +0100)]
Lua: garbage collect the simgrid module (remove simgrid.clean())
Christophe Thiéry [Thu, 10 Nov 2011 13:13:31 +0000 (14:13 +0100)]
Don't protect access to the metatable from Lua.
Lua code can never change the metatable of a userdata anyway
(setmetatable is possible only for a table).
getmetatable is now allowed for tasks and hosts: it's harmless and lets
people extend them.
Christophe Thiéry [Thu, 10 Nov 2011 13:06:13 +0000 (14:06 +0100)]
Clean MSG source file names
Martin Quinson [Thu, 10 Nov 2011 15:20:02 +0000 (16:20 +0100)]
inline static functions declared only once, and that were not really improving my execution flow understanding